多图谱方法在脑MR图像分割中的应用

doi:10.24920/003576

Highlight

Multi-atlas based methods for brain MR image segmentation were systematically reviewed in this review article. The author proposed that incorporating the anatomical prior into the end-to-end deep learning architectures, for brain ROI segmentation is an important direction in the future.

Abstract

Brain region-of-interesting (ROI) segmentation is an important prerequisite step for many computer-aid brain disease analyses. However, the human brain has the complicated anatomical structure. Meanwhile, the brain MR images often suffer from the low intensity contrast around the boundary of ROIs, large inter-subject variance and large inner-subject variance. To address these issues, many multi-atlas based segmentation methods are proposed for brain ROI segmentation in the last decade. In this paper, multi-atlas based methods for brain MR image segmentation were reviewed regarding several registration toolboxes which are widely used in the multi-atlas methods, conventional methods for label fusion, datasets that have been used for evaluating the multi-atlas methods, as well as the applications of multi-atlas based segmentation in clinical researches. We propose that incorporating the anatomical prior into the end-to-end deep learning architectures for brain ROI segmentation is an important direction in the future.

Key words: multi-atlas, brain, segmentation, magnetic resonance

Funding: Supported by the National Natural Science Foundation of China (Nos. 61876082, 61861130366, 61703301) and the Jiangsu Provincial 333 High-level Talent Cultivation Projects.

Sun Liang,Zhang Li,Zhang Daoqiang. Multi-Atlas Based Methods in Brain MR Image Segmentation[J].Chinese Medical Sciences Journal, 2019, 34(2): 110-119.

Figures/Tables 7

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Table 1

References 55

[1]	Devanand DP, Pradhaban G, Liu X , et al. Hippocampal and entorhinal atrophy in mild cognitive impairment - Prediction of Alzheimer disease. Neurology 2007; 68(11):828-36. doi: doi: 10.1212/01.wnl.0000256697.20968.d7
[2]	Zhang DQ, Wang YP, Zhou LP , et al. Multimodal classification of Alzheimer’s disease and mild cognitive impairment. Neuroimage 2011; 55(3):856-67. doi: doi: 10.1016/j.neuroimage.2011.01.008
[3]	Liu MX, Zhang DQ, Shen DG . Relationship induced multi-template learning for diagnosis of Alzheimer’s disease and mild cognitive impairment. IEEE Trans Med Imaging 2016; 35(6):1463-74. doi: doi: 10.1109/TMI.2016.2515021
[4]	Jie B, Liu MX, Zhang DQ , et al. Sub-network kernels for measuring similarity of brain connectivity networks in disease diagnosis. IEEE Trans Image Process 2018; 27(5):2340-53. doi: doi: 10.1109/TIP.2018.2799706
[5]	Liu MX, Zhang J, Adeli E , et al. Landmark-based deep multi-instance learning for brain disease diagnosis. Med Image Anal 2018; 43:157-68. doi: doi: 10.1016/j.media.2017.10.005
[6]	Jenkinson M, Smith S . A global optimisation method for robust affine registration of brain images. Med Image Anal 2001; 5(2):143-56. doi: doi: 10.1016/S1361-8415(01)00036-6
[7]	Langerak TR, van der Heide UA, Kotte ANTJ , et al. Improving label fusion in multi-atlas based segmentation by locally combining atlas selection and performance estimation. Comput Vision Image Understand 2015; 130:71-9. doi: doi: 10.1016/j.cviu.2014.09.004
[8]	Smith SM, Jenkinson M, Woolrich MW , et al. Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 2004; 23:S208-S19. doi: doi: 10.1016/j.neuroimage.2004.07.051
[9]	Avants BB, Epstein CL, Grossman M , et al. Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain. Med Image Anal 2008; 12(1):26-41. doi: doi: 10.1016/j.media.2007.06.004
[10]	Vercauteren T, Pennec X, Perchant A , et al. Diffeomorphic demons: Efficient non-parametric image registration. Neuroimage 2009; 45(1):S61-S72. doi: doi: 10.1016/j.neuroimage.2008.10.040
[11]	Thirion JP . Image matching as a diffusion process: an analogy with Maxwell’s demons. Med Image Anal 1998; 2(3):243-60. doi: doi: 10.1016/S1361-8415(98)80022-4
[12]	Warfield SK, Zou KH, Wells WM . Simultaneous truth and performance level estimation (STAPLE): An algorithm for the validation of image segmentation. IEEE Trans Med Imaging 2004; 23(7):903-21. doi: doi: 10.1109/TMI.2004.828354
[13]	Heckemann RA, Hajnal JV, Aljabar P , et al. Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. Neuroimage 2006; 33(1):115-26. doi: doi: 10.1016/j.neuroimage.2006.05.061
[14]	Artaechevarria X, Munoz-Barrutia A , Ortiz-de-Solorzano C. Combination strategies in multi-atlas image segmentation: application to brain MR data. IEEE Trans Med Imaging 2009; 28(8):1266-77. doi: doi: 10.1109/TMI.2009.2014372
[15]	Aljabar P, Heckemann RA, Hammers A , et al. Multi-atlas based segmentation of brain images: Atlas selection and its effect on accuracy. Neuroimage 2009; 46(3): 726-38. doi: . doi: 10.1016/j.neuroimage.2009.02.018
[16]	Lotjonen JMP, Wolz R, Koikkalainen JR , et al. Fast and robust multi-atlas segmentation of brain magnetic resonance images. Neuroimage 2010; 49(3):2352-65. doi: doi: 10.1016/j.neuroimage.2009.10.026
[17]	Sabuncu MR, Yeo BTT, Van Leemput K , et al. A Generative model for image segmentation based on label fusion. IEEE Trans Med Imaging 2010; 29(10):1714-29. doi: doi: 10.1109/TMI.2010.2050897
[18]	Langerak TR, van der Heide UA, Kotte ANTJ , et al. Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation (SIMPLE). IEEE Trans Med Imaging 2010; 29(12):2000-8. doi: doi: 10.1109/TMI.2010.2057442
[19]	L?tj?nen JM, Wolz R, Koikkalainen JR , et al. Fast and robust multi-atlas segmentation of brain magnetic resonance images. Neuroimage 2010; 49(3):2352-65. doi: 10.1016/j.neuroimage.2009.10.026
[20]	Langerak TR, van der Heide VA, Kotte ANTJ , et al. Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation (SIMPLE). IEEE Trans Med Imaging 2010; 29(12):2000-8. doi: doi: 10.1109/TMI.2010.2057442
[21]	Zhang DQ, Wu GR, Jia HJ , et al. Confidence-guided sequential label Fusion for multi-atlas based segmentation. Int Conference on Medical Image Computing and Computer-Assisted Intervention; 2011 September 18-22; Toronto, Canada. Berlin, Heidelberg: Springer; 2011. p 643-50. doi: . doi: 10.1007/978-3-642-23626-6_79
[22]	Coupé P, Manjon JV, Fonov V , et al. Patch-based segmentation using expert priors: Application to hippocampus and ventricle segmentation. Neuroimage 2011; 54(2):940-54. doi: doi: 10.1016/j.neuroimage.2010.09.018
[23]	Rousseau F, Habas PA, Studholme C . A supervised patch-based approach for human brain labeling. IEEE Trans Med Imaging 2011; 30(10):1852-62. doi: doi: 10.1109/TMI.2011.2156806
[24]	Zhang D, Guo Q, Wu G , et al., editors. Sparse patch-based label fusion for multi-atlas segmentation. International Workshop on Multimodal Brain Image Analysis. 2012 Oct 1-5; Nice, France. Berlin, Heidelberg: Springer; 2012. p 94-102. doi: . doi: 10.1007/978-3-642-33530-3_8
[25]	Wang HZ, Suh JW, Das SR , et al. Multi-atlas segmentation with joint label fusion. IEEE Trans Pattern Anal Machine Intell 2013; 35(3):611-23. doi: doi: 10.1109/TPAMI.2012.143
[26]	Wang HZ, Yushkevich PA . Groupwise segmentation with multi-atlas joint label fusion. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2013 Sep 22-26; Nagoya, Japan. Berlin, Heidelberg: Springer; 2013. p 711-8. doi: . doi: 10.1007/978-3-642-40811-3_89
[27]	Wang HZ, Yushkevich PA . Multi-atlas segmentation with joint label fusion and corrective learning — an open source implementation. Front Neuroinform 2013; 7. doi: . doi: 10.3389/fninf.2013.00027
[28]	Tong T, Wolz R, Coupe P , et al. Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling. Neuroimage 2013; 76(1):11-23. doi: doi: 10.1016/j.neuroimage.2013.02.069
[29]	Cardoso MJ, Leung K, Modat M , et al. STEPS: Similarity and Truth Estimation for Propagated Segmentations and its application to hippocampal segmentation and brain parcelation. Med Image Anal 2013; 17(6):671-84. doi: doi: 10.1016/j.media.2013.02.006
[30]	Wu GR, Wang Q, Zhang DQ , et al. A generative probability model of joint label fusion for multi-atlas based brain segmentation. Med Image Anal 2014; 18(6):881-90. doi: doi: 10.1016/j.media.2013.10.013
[31]	Sun L, Zu C, Zhang D . Reliability guided forward and backward patch-based method for multi-atlas segmentation. International Workshop on Patch-based Techniques in Medical Imaging; 2015 Oct 9; Munich, Germany. Cham: Springer; 2015. p 128-36. doi: . doi: 10.1007/978-3-319-28194-0_16
[32]	Wu GR, Kim MJ, Sanroma G , et al. Hierarchical multi-atlas label fusion with multi-scale feature representation and label-specific patch partition. Neuroimage 2015; 106:34-46. doi: doi: 10.1016/j.neuroimage.2014.11.025
[33]	Song Y, Wu G, Sun Q , et al. Progressive Label Fusion Framework for Multi-atlas Segmentation by Dictionary Evolution. International Conference on Medical Image Computing and Computer-Assisted Intervention; 2015 October 5-9; Munich, Germany. Cham: Springer; 2015: p 190-7. doi: . doi: 10.1007/978-3-319-24574-4_23
[34]	Benkarim OM, Piella G, Ballester MAG , et al. Discriminative confidence estimation for probabilistic multi-atlas label fusion. Med Image Anal 2017; 42:274-87. doi: doi: 10.1016/j.media.2017.08.008
[35]	Song YT, Wu GR, Bahrami K , et al. Progressive multi-atlas label fusion by dictionary evolution. Med Image Anal 2017; 36:162-71. doi: doi: 10.1016/j.media.2016.11.005
[36]	Zu C, Wang ZX, Zhang DQ , et al. Robust multi-atlas label propagation by deep sparse representation. Pattern Recognition 2017; 63:511-7. doi: doi: 10.1016/j.patcog.2016.09.028
[37]	Liang S, Wei S , Zhang D, editors. High-order boltzmann machine-based unsupervised feature learning for multi-atlas segmentation. IEEE International Symposium on Biomedical Imaging. 2017 Apr 18-21; Melbourne, Australia. New York: IEEE; 2017. p 507-10. doi: . doi: 10.1109/ISBI.2017.7950571
[38]	Sanroma G, Benkarim OM, Piella G , et al. Learning non-linear patch embeddings with neural networks for label fusion. Med Image Anal 2018; 44:143-55. doi: doi: 10.1016/j.media.2017.11.013
[39]	Huo J, Wu J, Cao JW , et al. Supervoxel based method for multi-atlas segmentation of brain MR images. Neuroimage 2018; 175:201-14. doi: doi: 10.1016/j.neuroimage.2018.04.001
[40]	Sun L, Zu C, Shao W , et al. Reliability-based robust multi-atlas label fusion for brain MRI segmentation. Artif Intell Med 2019; 96:12-24. doi: doi: 10.1016/j.artmed.2019.03.004
[41]	Kittler J . Combining classifiers: A theoretical framework. Pattern Anal App 1998; 1(1):18-27. doi: doi: 10.1007/BF01238023
[42]	Wang H, Yushkevich P . Multi-atlas segmentation with joint label fusion and corrective learning—an open source implementation. Front Neuroinform 2013; 7:27. doi: . doi: 10.3389/fninf.2013.00027
[43]	Zhang QA, Li BX . Discriminative K-SVD for Dictionary Learning in Face Recognition. IEEE Conference on Computer Vision and Pattern Recognition. 2010 Jun 13-18; San Francisco, CA, USA. New York: IEEE; 2010. p 2691-8. doi: . doi: 10.1109/Cvpr.2010.5539989
[44]	Yang M, Zhang L, Feng XC , et al. Fisher discrimination dictionary learning for sparse representation. International Conference on Computer Vision. 2011 Nov 6-13; Barcelona, Spain. New York: IEEE; 2011. p 543-50. doi: . doi: 10.1109/ICCV.2011.6126286
[45]	Ranzato M, Hinton GE . Modeling pixel means and covariances using factorized third-order boltzmann machines. IEEE Conference on Computer Vision and Pattern Recognition. 2010 Jun 13-18; San Francisco, CA, USA. New York: IEEE; 2010. p 2551-8. doi: . doi: 10.1109/CVPR.2010.5539962
[46]	Jack CR, Bernstein MA, Fox NC , et al. The Alzheimer’s disease neuroimaging initiative (ADNI): MRI methods. J Magnet Resonan Imaging 2008; 27(4):685-91. doi: doi: 10.1002/jmri.21049
[47]	Christensen GE, Geng X, Kuhl JG , et al. Introduction to the non-rigid image registration evaluation project (NIREP). IEEE Trans Magnet 2006; 30(5):2972-5. doi: doi: 10.1109/20.312561
[48]	Shattuck DW, Mirza M, Adisetiyo V , et al. Construction of a 3D probabilistic atlas of human cortical structures. Neuroimage 2008; 39(3):1064-80. doi: doi: 10.1016/j.neuroimage.2007.09.031
[49]	Evans AC, Collins DL, Mills SR , et al. 3D Statistical Neuroanatomical Models from 305 MRI Volumes. IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference. 1993 Oct 31 - Nov 6; San Francisco, CA, USA. New York: IEEE; 1993. 1813-7. doi: . doi: 10.1109/Nssmic.1993.373602
[50]	Makropoulos A, Gousias IS, Ledig C , et al. Automatic whole brain MRI segmentation of the developing neonatal brain. IEEE Trans Med Imaging 2014; 33(9):1818-31. doi: doi: 10.1109/TMI.2014.2322280
[51]	Aljabar P, Rueckert D, Crum WR . Automated morphological analysis of magnetic resonance brain imaging using spectral analysis. NeuroImage 2008; 43(2):225-35. doi: doi: 10.1016/j.neuroimage.2008.07.055
[52]	Pipitone J, Park MTM, Winterburn J , et al. Multi-atlas segmentation of the whole hippocampus and subfields using multiple automatically generated templates. Neuroimage 2014; 101:494-512. doi: doi: 10.1016/j.neuroimage.2014.04.054
[53]	Chen YJ, Gao HY, Cai L , et al. Voxel Deconvolutional Networks for 3D Brain Image Labeling. Kdd’18: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018 Aug 19-23; London, UK. New York: ACM; 2018. p 1226-34. doi: . doi: 10.1145/3219819.3219974
[54]	Ronneberger O, Fischer P, Brox T . U-Net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2015 Oct 5-9; Munich, Germany. Cham: Springer; 2015. p 234-41. doi: doi: 10.1007/978-3-319-24574-4_28
[55]	Shelhamer E, Long J, Darrell T . Fully Convolutional Networks for Semantic Segmentation. IEEE Trans Pattern Anal Machine Intell 2017; 39(4):640-51. doi: doi: 10.1109/TPAMI.2016.2572683

Methods	Subjects (n)	DR (%)	ASD	References No
LWJoint	139	89.7(88.8)	-	25
DDLS	202	87.2	-	28
HLF	66	88.5	0.334	32
Progressive SPBL	64	88.3	-	35
DSPBL	66	88.3	0.40	36
NL1	135	86.45	-	38

Early edition

Current issue

Archive

Specialties & Topics

Author center

Reviewer center

Multi-Atlas Based Methods in Brain MR Image Segmentation

RichHTML

PDF (PC)

Knowledge

Highlight

Abstract

Cite this article

share this article

Figures/Tables 7

References 55

Related Articles 15

Metrics

Recommended 10

[1]	Atefeh Beigi-khoozani, Amirmohammad Merajikhah, Mahdieh Soleimani. Magnetic Resonance Imaging Findings of Olfactory Bulb in Anosmic Patients with COVID-19: A Systematic Review [J]. Chinese Medical Sciences Journal, 2022, 37(1): 23-30.
[2]	Jia Xu, Xuan Wang, Zhengyu Jin, Qin Wang, Yan You, Shitian Wang, Tianyi Qian, Huadan Xue. Assessing Liver Function by T1 Maps on Gd-EOB-DTPA-Enhanced MRI for up to 50 Min in Rat Models of Liver Fibrosis: A Longer Hepatobiliary Time Period may Help [J]. Chinese Medical Sciences Journal, 2021, 36(2): 110-119.
[3]	Wang Xuedan, Wang Shiwei, Wang Botao, Chen Zhiye. Effect of MR Field Strength on the Texture Features of Cerebral T2-FLAIR Images: A Pilot Study [J]. Chinese Medical Sciences Journal, 2020, 35(3): 248-253.
[4]	Xu Yanhong,Yang Jia,Meng Jie,Wang Han. Targeted MR Imaging Adopting T1-Weighted Ultra-Small Iron Oxide Nanoparticles for Early Hepatocellular Carcinoma: An in vitro and in vivo Study [J]. Chinese Medical Sciences Journal, 2020, 35(2): 142-150.
[5]	Shi Ying-huan,Wang Qian. The Artificial Intelligence-Enabled Medical Imaging: Today and Its Future [J]. Chinese Medical Sciences Journal, 2019, 34(2): 71-75.
[6]	Guan Jian. Artificial Intelligence in Healthcare and Medicine: Promises, Ethical Challenges and Governance [J]. Chinese Medical Sciences Journal, 2019, 34(2): 76-83.
[7]	Xu Jia, Wang Xuan, Jin Zhengyu, You Yan, Wang Qin, Wang Shitian, Xue Huadan. Value of Texture Analysis on Gadoxetic Acid-enhanced MR for Detecting Liver Fibrosis in a Rat Model [J]. Chinese Medical Sciences Journal, 2019, 34(1): 24-32.
[8]	Wang Botao, Fan Wenping, Xu Huan, Li Lihui, Zhang Xiaohuan, Wang Kun, Liu Mengqi, You Junhao, Chen Zhiye. Value of Magnetic Resonance Imaging Texture Analysis in the Differential Diagnosis of Benign and Malignant Breast Tumors [J]. Chinese Medical Sciences Journal, 2019, 34(1): 33-37.
[9]	Li Ping, Zhu Liang, Wang Xuan, Xue Huadan, Wu Xin, Jin Zhengyu. Imaging Diagnosis of Type Ⅲ Choledochal Cyst: A Case Report [J]. Chinese Medical Sciences Journal, 2018, 33(3): 194-203.
[10]	Chen Zhiye, Liu Mengqi, Ma Lin. Cortical Thinning Pattern of Bulbar- and Spinal-onset Amyotrophic Lateral Sclerosis: a Surface-based Morphometry Study [J]. Chinese Medical Sciences Journal, 2018, 33(2): 100-106.
[11]	Li Lihui, Huang Houbin, Chen Zhiye. Early Diagnosis of Recurrent Optic Neuritis Using Contrast-Enhanced T2 Fluid-attenuated Inversion Recovery Imaging: a Case Report [J]. Chinese Medical Sciences Journal, 2018, 33(2): 130-134.
[12]	Chen Zhiye,Liu Mengqi,Ma Lin. Gray Matter Volume Changes over the Whole Brain in the Bulbar- and Spinal-onset Amyotrophic Lateral Sclerosis: a Voxel-based Morphometry Study [J]. Chinese Medical Sciences Journal, 2018, 33(1): 20-28.
[13]	Liu Yang,Liu Ziyuan,Wan Xinhua,Guo Yi. Progress in the Diagnosis and Management of Chorea-acanthocytosis [J]. Chinese Medical Sciences Journal, 2018, 33(1): 53-59.
[14]	Liu Mengqi, Chen Zhiye, Ma Lin. Reliability of Three Dimentional Pseudo-continuous Arterial Spin Labeling: A Volumetric Cerebral Perfusion Imaging with Different Post-labeling Time and Functional State in Health Adults [J]. Chinese Medical Sciences Journal, 2018, 33(1): 38-44.
[15]	Chen Zhiye, Liu Mengqi, Ma Lin. Surface-Based Morphometry of Human Brain: Intra-Individual Comparison Between 3T and 7T High Resolution Structural MR Imaging^△ [J]. Chinese Medical Sciences Journal, 2017, 32(4): 226-231.